You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Patrick Wendell (JIRA)" <ji...@apache.org> on 2014/07/27 20:08:38 UTC
[jira] [Commented] (SPARK-2677) BasicBlockFetchIterator#next can
wait forever
[ https://issues.apache.org/jira/browse/SPARK-2677?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14075672#comment-14075672 ]
Patrick Wendell commented on SPARK-2677:
----------------------------------------
Just as an FYI - this has been observed also in several earlier versions of Spark. I think one issue is that we don't have timeouts in the conneciton manger code. If a JVM goes into GC thrashing and becomes un-responsive (but still alive), then you can get stuck here.
> BasicBlockFetchIterator#next can wait forever
> ---------------------------------------------
>
> Key: SPARK-2677
> URL: https://issues.apache.org/jira/browse/SPARK-2677
> Project: Spark
> Issue Type: Bug
> Components: Spark Core
> Affects Versions: 0.9.2, 1.0.0, 1.0.1
> Reporter: Kousuke Saruta
> Priority: Blocker
>
> In BasicBlockFetchIterator#next, it waits fetch result on result.take.
> {code}
> override def next(): (BlockId, Option[Iterator[Any]]) = {
> resultsGotten += 1
> val startFetchWait = System.currentTimeMillis()
> val result = results.take()
> val stopFetchWait = System.currentTimeMillis()
> _fetchWaitTime += (stopFetchWait - startFetchWait)
> if (! result.failed) bytesInFlight -= result.size
> while (!fetchRequests.isEmpty &&
> (bytesInFlight == 0 || bytesInFlight + fetchRequests.front.size <= maxBytesInFlight)) {
> sendRequest(fetchRequests.dequeue())
> }
> (result.blockId, if (result.failed) None else Some(result.deserialize()))
> }
> {code}
> But, results is implemented as LinkedBlockingQueue so if remote executor hang up, fetching Executor waits forever.
--
This message was sent by Atlassian JIRA
(v6.2#6252)